제로베이스 데이터취업스쿨 DAY22 웹 데이터 분석1~4

• 사용법 다르다.
  -find, findall : soup.find("p", class="inner-text first-item")
  -select_one, select : soup.select("#exchangeList > li")

• 두 가지 모듈
  -from urllib.request import urlopen
  -import requests

네이버 금융데이터 가져오기

from urllib.request import urlopen
from bs4 import BeautifulSoup

url = "https://finance.naver.com/marketindex/"
page = urlopen(url)
soup = BeautifulSoup(page, "html.parser")
print(soup.prettify())
soup.find_all("span", "value")
# span 태그의 value 클래스

#- find, select_one : 단일선택
#- find_all, select : 다중선택

import requests
from bs4 import BeautifulSoup

url = "https://finance.naver.com/marketindex/"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
print(soup.prettify())

# id => #,  class => .
exchangeList = soup.select("#exchangeList > li")

exchange_datas = []
baseUrl = "https://finance.naver.com"

for item in exchangeList:
    data = {
        "title" : item.select_one(".h_lst").text,
        "exchange" : item.select_one(".value").text,
        "change" : item.select_one(".change").text,
        "updown" : item.select_one("div.head_info.point_up > .blind").text,
        "link" : baseUrl + item.select_one("a").get("href")
    }
    exchange_datas.append(data)
df = pd.DataFrame(exchange_datas)
df.to_excel("./naverfinance.xlsx", encoding="utf-8")

위키백과 문서정보 가져오기

import urllib
from urllib.request import urlopen, Request

html = "https://ko.wikipedia.org/wiki/{search_words}"
req = Request(html.format(search_words=urllib.parse.quote("여명의_눈동자"))) # 글자를 URL로 인코딩
response = urlopen(req)
soup = BeautifulSoup(response, "html.parser")

soup.find_all("ul")[32].text.strip().replace("\xa0", "").replace("\n", "")